yolov5-face

yolov5-face copied to clipboard

yolov5版本

1

作者你好，请问你这个工程是基于yolov5的那个版本修改的？

CV-deeplearning

调整下hyp里面的权重。

4

调整下hyp里面的权重。 _Originally posted by @derronqi in https://github.com/deepcam-cn/yolov5-face/issues/99#issuecomment-982254928_

sssssshf

Multi-Task-Facial training images

3

In the README, you have mentioned "2021.08: Add new training dataset Multi-Task-Facial improve large face detection." Where can I find the images of this dataset?

manisoftwartist

关于face_datasets.py 308行数据预处理

1

请问经过letterbox后，关键点的标签为什么不用这种方式更新 #labels[:, 5] = ratio[0] * w * x[:, 5] + pad[0] 而是采用了下面这种方式 labels[:, 5] = np.array(x[:, 5] > 0, dtype=np.int32) * (ratio[0] * w * x[:, 5] + pad[0])...

liu0623

TensorRT questions

8

Using yolov5n-0.5.pt on Jetson Nano and Get about 5 fps And I try to use tensorRT So I first using models/export.py and torch2tensorrt/main.py to do inference And I get some...

Jim0530

训练技巧

2

大佬不吝赐教 1 训练时如何取的 detec和landmark的均衡性能？两个任务都会到较好的性能点 2 我训练时 关注更精准的landmark 增加了一批celeba等 小人脸检测性能下降该怎么办？

sssssshf

choose proper "img_size"?

1

Hi. in `detect_face.py` there is a parameter, `img_size=2048`.This parameter has huge impact on inference time and preprocessing but reducing it comes with reduction of accuracy... How did you choose this...

hamid-mp

.cpp:863: virtual nvinfer1::ILayer* nvinfer1::Network::getLayer(int) const: Assertion `layerIndex >= 0' failed.

6

运行环境  

Bob-jpg

@derronqi 你好，我也有差不多得疑问，我就是想请教一下，yolo.py中关于5个点推理部分，这个怎么理解呢，我看有点像中心点和宽高推理得融合，不是很理解，能麻烦解释一下吗

CompliceU

How to test widerface

2

Hi How step to test widerface? how to put the image and the image label?

joynjo